A fuzzy treatment of uncertain Markov decision processes : Average case (Mathematical Decision Making under uncertainty and ambiguity)
A fuzzy treatment of uncertain Markov decision processes : Average case (Mathematical Decision Making under uncertainty and ambiguity)
复制标题
不确定马尔可夫决策过程的模糊处理：平均情况（不确定性和模糊性下的数学决策）
DOI：
--
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
Y. Yoshida
中科院分区：
文献类型：
--
作者：
M. Kurano;Masami Yausda;J. Nakagami;Y. Yoshida
本文利用模糊集描述非齐次马尔可夫决策过程的不确定转移矩阵。引入 ν 步收缩属性（称为次要化条件），对于平均情况，我们改进了帕累托最优策略，在某些偏序下最大化平均预期模糊奖励。帕累托最优策略的特征是包含有效集合函数的最优方程的最大解。
In this paper, the uncertain transition matrices for inhomogeneous Markov decision processes are described by use of fuzzy sets. Introducing a ν-step contractive property, called a minorization condition, for the average case, we fined a Pareto optimal policy maximizing the average expected fuzzy rewards under some partial order. The Pareto optimal policies are characterized by maximal solutions of an optimal equation including efficient set-functions.